Title: Predicting the effects of tool geometries on friction stirred aluminium welds using artificial neural networks and fuzzy logic techniques

Authors: H.K. Mohanty; M.M. Mahapatra; Pradeep Kumar; Pankaj Biswas; Nisith Ranjan Mandal

Addresses: Mechanical and Industrial Engineering Department, IIT, Roorkee-247667, India ' Mechanical and Industrial Engineering Department, IIT, Roorkee-247667, India ' Mechanical and Industrial Engineering Department, IIT, Roorkee-247667, India ' Department of Mechanical Engineering, IIT, Guwahati-781039, India ' Department of Ocean Engineering and Naval Architecture, IIT, Kharagpur-721302, India

Abstract: Effect of friction stir welding (FSW) tool geometries on aluminium welds were investigated using different tool shoulder and pin probe geometry profiles. A combination of 27 tool shoulder and pin profile geometries were used for the experimental purpose using a design matrix. The effect of these tool geometries on the friction stir welds like the weld strength, weld cross-section area and grain sizes were investigated. The effects of the tool geometries were predicted using artificial intelligence techniques such as artificial neural networks (ANN) and fuzzy logic modelling. It was observed that, for a combination of FSW tool geometries, the ANN model was not so effective in predicting the FSW weldment characteristics, while the fuzzy logic model was able to predict the same with much lower percentage of error for the test cases. [Received 4 January 2012; Revised 9 August 2012; Accepted 26 December 2012]

Keywords: friction stir welding; FSW; tool shoulder; tool pin probe profile; weld strength; tool geometries; aluminium welds; artificial neural networks; ANNs; fuzzy logic; grain size; modelling.

DOI: 10.1504/IJMR.2013.055245

International Journal of Manufacturing Research, 2013 Vol.8 No.3, pp.296 - 312

Published online: 29 Jan 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article